* [PATCH v8 1/6] iommu: rename iommu_dom0_strict and iommu_passthrough
2018-09-07 9:07 [PATCH v8 0/6] x86/iommu: PVH Dom0 workarounds for missing RMRR entries Roger Pau Monne
@ 2018-09-07 9:07 ` Roger Pau Monne
2018-09-12 8:22 ` Roger Pau Monné
2018-09-12 11:53 ` Suravee Suthikulpanit
2018-09-07 9:07 ` [PATCH v8 2/6] iommu: introduce dom0-iommu option Roger Pau Monne
` (4 subsequent siblings)
5 siblings, 2 replies; 14+ messages in thread
From: Roger Pau Monne @ 2018-09-07 9:07 UTC (permalink / raw)
To: xen-devel
Cc: Kevin Tian, Jan Beulich, Andrew Cooper, Suravee Suthikulpanit,
Brian Woods, Roger Pau Monne
To iommu_hwdom_strict and iommu_hwdom_passthrough which is more
descriptive of their usage. Also change their type from bool_t to
bool.
No functional change.
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Wei Liu <wei.liu2@citrix.com>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Cc: Brian Woods <brian.woods@amd.com>
Cc: Kevin Tian <kevin.tian@intel.com>
---
Changes since v5:
- Remove unneeded !!.
Changes since v4:
- New in this version.
---
xen/arch/x86/x86_64/mm.c | 3 ++-
xen/drivers/passthrough/amd/iommu_init.c | 2 +-
xen/drivers/passthrough/amd/pci_amd_iommu.c | 4 +--
xen/drivers/passthrough/iommu.c | 27 +++++++++++----------
xen/drivers/passthrough/vtd/iommu.c | 16 ++++++------
xen/drivers/passthrough/vtd/x86/vtd.c | 2 +-
xen/include/xen/iommu.h | 6 +++--
7 files changed, 32 insertions(+), 28 deletions(-)
diff --git a/xen/arch/x86/x86_64/mm.c b/xen/arch/x86/x86_64/mm.c
index 989a53463a..b08d10755b 100644
--- a/xen/arch/x86/x86_64/mm.c
+++ b/xen/arch/x86/x86_64/mm.c
@@ -1426,7 +1426,8 @@ int memory_add(unsigned long spfn, unsigned long epfn, unsigned int pxm)
if ( ret )
goto destroy_m2p;
- if ( iommu_enabled && !iommu_passthrough && !need_iommu(hardware_domain) )
+ if ( iommu_enabled && !iommu_hwdom_passthrough &&
+ !need_iommu(hardware_domain) )
{
for ( i = spfn; i < epfn; i++ )
if ( iommu_map_page(hardware_domain, i, i, IOMMUF_readable|IOMMUF_writable) )
diff --git a/xen/drivers/passthrough/amd/iommu_init.c b/xen/drivers/passthrough/amd/iommu_init.c
index 474992a75a..15c10b0929 100644
--- a/xen/drivers/passthrough/amd/iommu_init.c
+++ b/xen/drivers/passthrough/amd/iommu_init.c
@@ -1062,7 +1062,7 @@ static void __init amd_iommu_init_cleanup(void)
radix_tree_destroy(&ivrs_maps, xfree);
iommu_enabled = 0;
- iommu_passthrough = 0;
+ iommu_hwdom_passthrough = false;
iommu_intremap = 0;
iommuv2_enabled = 0;
}
diff --git a/xen/drivers/passthrough/amd/pci_amd_iommu.c b/xen/drivers/passthrough/amd/pci_amd_iommu.c
index 12d2695b89..ab39e7500d 100644
--- a/xen/drivers/passthrough/amd/pci_amd_iommu.c
+++ b/xen/drivers/passthrough/amd/pci_amd_iommu.c
@@ -121,7 +121,7 @@ static void amd_iommu_setup_domain_device(
BUG_ON( !hd->arch.root_table || !hd->arch.paging_mode ||
!iommu->dev_table.buffer );
- if ( iommu_passthrough && is_hardware_domain(domain) )
+ if ( iommu_hwdom_passthrough && is_hardware_domain(domain) )
valid = 0;
if ( ats_enabled )
@@ -256,7 +256,7 @@ static void __hwdom_init amd_iommu_hwdom_init(struct domain *d)
if ( allocate_domain_resources(dom_iommu(d)) )
BUG();
- if ( !iommu_passthrough && !need_iommu(d) )
+ if ( !iommu_hwdom_passthrough && !need_iommu(d) )
{
int rc = 0;
diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index 70d218f910..729ee5c373 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -52,15 +52,16 @@ custom_param("iommu", parse_iommu_param);
bool_t __initdata iommu_enable = 1;
bool_t __read_mostly iommu_enabled;
bool_t __read_mostly force_iommu;
-bool_t __hwdom_initdata iommu_dom0_strict;
bool_t __read_mostly iommu_verbose;
bool_t __read_mostly iommu_workaround_bios_bug;
bool_t __read_mostly iommu_igfx = 1;
-bool_t __read_mostly iommu_passthrough;
bool_t __read_mostly iommu_snoop = 1;
bool_t __read_mostly iommu_qinval = 1;
bool_t __read_mostly iommu_intremap = 1;
+bool __hwdom_initdata iommu_hwdom_strict;
+bool __read_mostly iommu_hwdom_passthrough;
+
/*
* In the current implementation of VT-d posted interrupts, in some extreme
* cases, the per cpu list which saves the blocked vCPU will be very long,
@@ -121,9 +122,9 @@ static int __init parse_iommu_param(const char *s)
else if ( !strncmp(s, "amd-iommu-perdev-intremap", ss - s) )
amd_iommu_perdev_intremap = val;
else if ( !strncmp(s, "dom0-passthrough", ss - s) )
- iommu_passthrough = val;
+ iommu_hwdom_passthrough = val;
else if ( !strncmp(s, "dom0-strict", ss - s) )
- iommu_dom0_strict = val;
+ iommu_hwdom_strict = val;
else if ( !strncmp(s, "sharept", ss - s) )
iommu_hap_pt_share = val;
else
@@ -158,11 +159,11 @@ static void __hwdom_init check_hwdom_reqs(struct domain *d)
arch_iommu_check_autotranslated_hwdom(d);
- if ( iommu_passthrough )
+ if ( iommu_hwdom_passthrough )
panic("Dom0 uses paging translated mode, dom0-passthrough must not be "
"enabled\n");
- iommu_dom0_strict = 1;
+ iommu_hwdom_strict = true;
}
void __hwdom_init iommu_hwdom_init(struct domain *d)
@@ -175,7 +176,7 @@ void __hwdom_init iommu_hwdom_init(struct domain *d)
return;
register_keyhandler('o', &iommu_dump_p2m_table, "dump iommu p2m table", 0);
- d->need_iommu = !!iommu_dom0_strict;
+ d->need_iommu = iommu_hwdom_strict;
if ( need_iommu(d) && !iommu_use_hap_pt(d) )
{
struct page_info *page;
@@ -371,8 +372,8 @@ int __init iommu_setup(void)
int rc = -ENODEV;
bool_t force_intremap = force_iommu && iommu_intremap;
- if ( iommu_dom0_strict )
- iommu_passthrough = 0;
+ if ( iommu_hwdom_strict )
+ iommu_hwdom_passthrough = false;
if ( iommu_enable )
{
@@ -393,15 +394,15 @@ int __init iommu_setup(void)
if ( !iommu_enabled )
{
iommu_snoop = 0;
- iommu_passthrough = 0;
- iommu_dom0_strict = 0;
+ iommu_hwdom_passthrough = false;
+ iommu_hwdom_strict = false;
}
printk("I/O virtualisation %sabled\n", iommu_enabled ? "en" : "dis");
if ( iommu_enabled )
{
printk(" - Dom0 mode: %s\n",
- iommu_passthrough ? "Passthrough" :
- iommu_dom0_strict ? "Strict" : "Relaxed");
+ iommu_hwdom_passthrough ? "Passthrough" :
+ iommu_hwdom_strict ? "Strict" : "Relaxed");
printk("Interrupt remapping %sabled\n", iommu_intremap ? "en" : "dis");
tasklet_init(&iommu_pt_cleanup_tasklet, iommu_free_pagetables, 0);
}
diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index 1710256823..32bf0fc299 100644
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -1304,7 +1304,7 @@ static void __hwdom_init intel_iommu_hwdom_init(struct domain *d)
{
struct acpi_drhd_unit *drhd;
- if ( !iommu_passthrough && is_pv_domain(d) )
+ if ( !iommu_hwdom_passthrough && is_pv_domain(d) )
{
/* Set up 1:1 page table for hardware domain. */
vtd_set_hwdom_mapping(d);
@@ -1391,7 +1391,7 @@ int domain_context_mapping_one(
return res;
}
- if ( iommu_passthrough && is_hardware_domain(domain) )
+ if ( iommu_hwdom_passthrough && is_hardware_domain(domain) )
{
context_set_translation_type(*context, CONTEXT_TT_PASS_THRU);
agaw = level_to_agaw(iommu->nr_pt_levels);
@@ -1781,7 +1781,7 @@ static int __must_check intel_iommu_map_page(struct domain *d,
return 0;
/* Do nothing if hardware domain and iommu supports pass thru. */
- if ( iommu_passthrough && is_hardware_domain(d) )
+ if ( iommu_hwdom_passthrough && is_hardware_domain(d) )
return 0;
spin_lock(&hd->arch.mapping_lock);
@@ -1826,7 +1826,7 @@ static int __must_check intel_iommu_unmap_page(struct domain *d,
unsigned long gfn)
{
/* Do nothing if hardware domain and iommu supports pass thru. */
- if ( iommu_passthrough && is_hardware_domain(d) )
+ if ( iommu_hwdom_passthrough && is_hardware_domain(d) )
return 0;
return dma_pte_clear_one(d, (paddr_t)gfn << PAGE_SHIFT_4K);
@@ -2269,8 +2269,8 @@ int __init intel_vtd_setup(void)
if ( iommu_snoop && !ecap_snp_ctl(iommu->ecap) )
iommu_snoop = 0;
- if ( iommu_passthrough && !ecap_pass_thru(iommu->ecap) )
- iommu_passthrough = 0;
+ if ( iommu_hwdom_passthrough && !ecap_pass_thru(iommu->ecap) )
+ iommu_hwdom_passthrough = false;
if ( iommu_qinval && !ecap_queued_inval(iommu->ecap) )
iommu_qinval = 0;
@@ -2308,7 +2308,7 @@ int __init intel_vtd_setup(void)
#define P(p,s) printk("Intel VT-d %s %senabled.\n", s, (p)? "" : "not ")
P(iommu_snoop, "Snoop Control");
- P(iommu_passthrough, "Dom0 DMA Passthrough");
+ P(iommu_hwdom_passthrough, "Dom0 DMA Passthrough");
P(iommu_qinval, "Queued Invalidation");
P(iommu_intremap, "Interrupt Remapping");
P(iommu_intpost, "Posted Interrupt");
@@ -2330,7 +2330,7 @@ int __init intel_vtd_setup(void)
error:
iommu_enabled = 0;
iommu_snoop = 0;
- iommu_passthrough = 0;
+ iommu_hwdom_passthrough = false;
iommu_qinval = 0;
iommu_intremap = 0;
iommu_intpost = 0;
diff --git a/xen/drivers/passthrough/vtd/x86/vtd.c b/xen/drivers/passthrough/vtd/x86/vtd.c
index ac653eea0e..ef1a02cba6 100644
--- a/xen/drivers/passthrough/vtd/x86/vtd.c
+++ b/xen/drivers/passthrough/vtd/x86/vtd.c
@@ -103,7 +103,7 @@ void __hwdom_init vtd_set_hwdom_mapping(struct domain *d)
* If dom0-strict mode is enabled then exclude conventional RAM
* and let the common code map dom0's pages.
*/
- if ( iommu_dom0_strict &&
+ if ( iommu_hwdom_strict &&
page_is_ram_type(pfn, RAM_TYPE_CONVENTIONAL) )
continue;
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index e35d941f3c..392cf1e6b9 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -29,13 +29,15 @@
#include <asm/iommu.h>
extern bool_t iommu_enable, iommu_enabled;
-extern bool_t force_iommu, iommu_dom0_strict, iommu_verbose;
-extern bool_t iommu_workaround_bios_bug, iommu_igfx, iommu_passthrough;
+extern bool_t force_iommu, iommu_verbose;
+extern bool_t iommu_workaround_bios_bug, iommu_igfx;
extern bool_t iommu_snoop, iommu_qinval, iommu_intremap, iommu_intpost;
extern bool_t iommu_hap_pt_share;
extern bool_t iommu_debug;
extern bool_t amd_iommu_perdev_intremap;
+extern bool iommu_hwdom_strict, iommu_hwdom_passthrough;
+
extern unsigned int iommu_dev_iotlb_timeout;
int iommu_setup(void);
--
2.18.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 14+ messages in thread* Re: [PATCH v8 1/6] iommu: rename iommu_dom0_strict and iommu_passthrough
2018-09-07 9:07 ` [PATCH v8 1/6] iommu: rename iommu_dom0_strict and iommu_passthrough Roger Pau Monne
@ 2018-09-12 8:22 ` Roger Pau Monné
2018-09-12 11:53 ` Suravee Suthikulpanit
1 sibling, 0 replies; 14+ messages in thread
From: Roger Pau Monné @ 2018-09-12 8:22 UTC (permalink / raw)
To: Suravee Suthikulpanit, Brian Woods
Cc: xen-devel, Kevin Tian, Jan Beulich, Andrew Cooper
On Fri, Sep 07, 2018 at 11:07:34AM +0200, Roger Pau Monne wrote:
> To iommu_hwdom_strict and iommu_hwdom_passthrough which is more
> descriptive of their usage. Also change their type from bool_t to
> bool.
>
> No functional change.
>
> Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
> Reviewed-by: Jan Beulich <jbeulich@suse.com>
> Reviewed-by: Kevin Tian <kevin.tian@intel.com>
> Reviewed-by: Wei Liu <wei.liu2@citrix.com>
> ---
> Cc: Jan Beulich <jbeulich@suse.com>
> Cc: Andrew Cooper <andrew.cooper3@citrix.com>
> Cc: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
> Cc: Brian Woods <brian.woods@amd.com>
Ping?
Can I please get an Ack or otherwise from the AMD IOMMU maintainers?
Thanks. Roger.
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH v8 1/6] iommu: rename iommu_dom0_strict and iommu_passthrough
2018-09-07 9:07 ` [PATCH v8 1/6] iommu: rename iommu_dom0_strict and iommu_passthrough Roger Pau Monne
2018-09-12 8:22 ` Roger Pau Monné
@ 2018-09-12 11:53 ` Suravee Suthikulpanit
1 sibling, 0 replies; 14+ messages in thread
From: Suravee Suthikulpanit @ 2018-09-12 11:53 UTC (permalink / raw)
To: Roger Pau Monne, xen-devel
Cc: Andrew Cooper, Kevin Tian, Brian Woods, Jan Beulich
Roger,
On 9/7/18 4:07 PM, Roger Pau Monne wrote:
> To iommu_hwdom_strict and iommu_hwdom_passthrough which is more
> descriptive of their usage. Also change their type from bool_t to
> bool.
>
> No functional change.
>
> Signed-off-by: Roger Pau Monné<roger.pau@citrix.com>
> Reviewed-by: Jan Beulich<jbeulich@suse.com>
> Reviewed-by: Kevin Tian<kevin.tian@intel.com>
> Reviewed-by: Wei Liu<wei.liu2@citrix.com>
> ---
> Cc: Jan Beulich<jbeulich@suse.com>
> Cc: Andrew Cooper<andrew.cooper3@citrix.com>
> Cc: Suravee Suthikulpanit<suravee.suthikulpanit@amd.com>
> Cc: Brian Woods<brian.woods@amd.com>
> Cc: Kevin Tian<kevin.tian@intel.com>
> ---
> Changes since v5:
> - Remove unneeded !!.
>
> Changes since v4:
> - New in this version
Acked-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Thank you,
Suravee
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 14+ messages in thread
* [PATCH v8 2/6] iommu: introduce dom0-iommu option
2018-09-07 9:07 [PATCH v8 0/6] x86/iommu: PVH Dom0 workarounds for missing RMRR entries Roger Pau Monne
2018-09-07 9:07 ` [PATCH v8 1/6] iommu: rename iommu_dom0_strict and iommu_passthrough Roger Pau Monne
@ 2018-09-07 9:07 ` Roger Pau Monne
2018-09-07 9:07 ` [PATCH v8 3/6] iommu: make iommu_inclusive_mapping a suboption of dom0-iommu Roger Pau Monne
` (3 subsequent siblings)
5 siblings, 0 replies; 14+ messages in thread
From: Roger Pau Monne @ 2018-09-07 9:07 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk, George Dunlap,
Andrew Cooper, Ian Jackson, Tim Deegan, Julien Grall, Jan Beulich,
Roger Pau Monne
To select the iommu configuration used by Dom0. This option supersedes
iommu=dom0-strict|dom0-passthrough.
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Wei Liu <wei.liu2@citrix.com>
---
Changes since v5:
- Fix typo in docs.
- Force iommu_hwdom_passthrough to false for PVH Dom0. Note this in
the documentation.
Changes since v4:
- Move the iommu_dom0_* variable renaming to a previous patch.
- Use dom0-iommu=passthrough|strict booleans, like the iommu option
used.
Changes since v2:
- Change the style and text used in the xen command line document.
- Don't allow none, strict or relaxed to use the no- prefix.
Changes since v1:
- New in this version.
---
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Julien Grall <julien.grall@arm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tim Deegan <tim@xen.org>
Cc: Wei Liu <wei.liu2@citrix.com>
---
docs/misc/xen-command-line.markdown | 21 +++++++++++++++++++
xen/drivers/passthrough/iommu.c | 31 +++++++++++++++++++++++++----
2 files changed, 48 insertions(+), 4 deletions(-)
diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown
index 559c0662fa..cd57960ede 100644
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -681,6 +681,21 @@ Flag that makes a dom0 boot in PVHv2 mode.
Flag that makes a dom0 use shadow paging. Only works when "pvh" is
enabled.
+### dom0-iommu
+> `= List of [ passthrough | strict ]`
+
+This list of booleans controls the iommu usage by Dom0:
+
+* `passthrough`: disables DMA remapping for Dom0. Default is `false`. Note that
+ this option is hard coded to `false` for a PVH Dom0 and any attempt to
+ overwrite it from the command line is ignored.
+
+* `strict`: sets up DMA remapping only for the RAM Dom0 actually got assigned.
+ Default is `false` which means Dom0 will get mappings for all the host
+ RAM except regions in use by Xen. Note that this option is hard coded to
+ `true` for a PVH Dom0 and any attempt to overwrite it from the command line
+ is ignored.
+
### dom0\_ioports\_disable (x86)
> `= List of <hex>-<hex>`
@@ -1152,12 +1167,18 @@ detection of systems known to misbehave upon accesses to that port.
> `dom0-passthrough`
+> **WARNING: This command line option is deprecated, and superseded by
+> _dom0-iommu=passthrough_ - using both options in combination is undefined.**
+
> Default: `false`
>> Control whether to disable DMA remapping for Dom0.
> `dom0-strict`
+> **WARNING: This command line option is deprecated, and superseded by
+> _dom0-iommu=strict_ - using both options in combination is undefined.**
+
> Default: `false`
>> Control whether to set up DMA remapping only for the memory Dom0 actually
diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index 729ee5c373..8f9975cf4e 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -136,6 +136,32 @@ static int __init parse_iommu_param(const char *s)
return rc;
}
+static int __init parse_dom0_iommu_param(const char *s)
+{
+ const char *ss;
+ int rc = 0;
+
+ do {
+ int val;
+
+ ss = strchr(s, ',');
+ if ( !ss )
+ ss = strchr(s, '\0');
+
+ if ( (val = parse_boolean("passthrough", s, ss)) >= 0 )
+ iommu_hwdom_passthrough = val;
+ else if ( (val = parse_boolean("strict", s, ss)) >= 0 )
+ iommu_hwdom_strict = val;
+ else
+ rc = -EINVAL;
+
+ s = ss + 1;
+ } while ( *ss );
+
+ return rc;
+}
+custom_param("dom0-iommu", parse_dom0_iommu_param);
+
int iommu_domain_init(struct domain *d)
{
struct domain_iommu *hd = dom_iommu(d);
@@ -159,10 +185,7 @@ static void __hwdom_init check_hwdom_reqs(struct domain *d)
arch_iommu_check_autotranslated_hwdom(d);
- if ( iommu_hwdom_passthrough )
- panic("Dom0 uses paging translated mode, dom0-passthrough must not be "
- "enabled\n");
-
+ iommu_hwdom_passthrough = false;
iommu_hwdom_strict = true;
}
--
2.18.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v8 3/6] iommu: make iommu_inclusive_mapping a suboption of dom0-iommu
2018-09-07 9:07 [PATCH v8 0/6] x86/iommu: PVH Dom0 workarounds for missing RMRR entries Roger Pau Monne
2018-09-07 9:07 ` [PATCH v8 1/6] iommu: rename iommu_dom0_strict and iommu_passthrough Roger Pau Monne
2018-09-07 9:07 ` [PATCH v8 2/6] iommu: introduce dom0-iommu option Roger Pau Monne
@ 2018-09-07 9:07 ` Roger Pau Monne
2018-09-10 11:30 ` Julien Grall
2018-09-12 11:59 ` Suravee Suthikulpanit
2018-09-07 9:07 ` [PATCH v8 4/6] mm: introduce a helper to get the memory type of a page Roger Pau Monne
` (2 subsequent siblings)
5 siblings, 2 replies; 14+ messages in thread
From: Roger Pau Monne @ 2018-09-07 9:07 UTC (permalink / raw)
To: xen-devel
Cc: Kevin Tian, Stefano Stabellini, Wei Liu, Suravee Suthikulpanit,
Konrad Rzeszutek Wilk, George Dunlap, Andrew Cooper, Ian Jackson,
Tim Deegan, Julien Grall, Jan Beulich, Brian Woods,
Roger Pau Monne
Introduce a new dom0-iommu=map-inclusive generic option that
supersedes iommu_inclusive_mapping. The previous behavior is preserved
and the option should only be enabled by default on Intel hardware.
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
---
Changes since v7:
- Use -1, 0, 1 in iommu_hwdom_inclusive.
- Print a warning message if map-inclusive is set on ARM.
Changes since v4:
- Use an if to set the default option value.
- Set the option to false unconditionally on ARM.
Changes since v2:
- Fix typo in commit message.
- Change style and text of the documentation in xen command line.
- Set the defaults in {intel/amd}_iommu_hwdom_init for inclusive.
- Re-add the iommu_dom0_passthrough || !is_pv_domain(d) check.
Changes since v1:
- Use dom0-iommu instead of the iommu option.
- Only enable by default on Intel hardware.
---
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Julien Grall <julien.grall@arm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tim Deegan <tim@xen.org>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Cc: Brian Woods <brian.woods@amd.com>
Cc: Kevin Tian <kevin.tian@intel.com>
---
docs/misc/xen-command-line.markdown | 13 ++++-
xen/drivers/passthrough/amd/pci_amd_iommu.c | 4 ++
xen/drivers/passthrough/arm/iommu.c | 4 ++
xen/drivers/passthrough/arm/smmu.c | 5 ++
xen/drivers/passthrough/iommu.c | 13 +++++
xen/drivers/passthrough/vtd/extern.h | 2 -
xen/drivers/passthrough/vtd/iommu.c | 8 ++-
xen/drivers/passthrough/vtd/x86/vtd.c | 58 +-------------------
xen/drivers/passthrough/x86/iommu.c | 59 +++++++++++++++++++++
xen/include/xen/iommu.h | 2 +
10 files changed, 103 insertions(+), 65 deletions(-)
diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown
index cd57960ede..98f0f3b68b 100644
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -682,7 +682,7 @@ Flag that makes a dom0 use shadow paging. Only works when "pvh" is
enabled.
### dom0-iommu
-> `= List of [ passthrough | strict ]`
+> `= List of [ passthrough | strict | map-inclusive ]`
This list of booleans controls the iommu usage by Dom0:
@@ -696,6 +696,14 @@ This list of booleans controls the iommu usage by Dom0:
`true` for a PVH Dom0 and any attempt to overwrite it from the command line
is ignored.
+* `map-inclusive`: sets up DMA remapping for all the non-RAM regions below 4GB
+ except for unusable ranges. Use this to work around firmware issues providing
+ incorrect RMRR/IVMD entries. Rather than only mapping RAM pages for IOMMU
+ accesses for Dom0, with this option all pages up to 4GB, not marked as
+ unusable in the E820 table, will get a mapping established. Note that this
+ option is only applicable to a PV Dom0 and is enabled by default on Intel
+ hardware.
+
### dom0\_ioports\_disable (x86)
> `= List of <hex>-<hex>`
@@ -1233,6 +1241,9 @@ wait descriptor timed out', try increasing this value.
### iommu\_inclusive\_mapping (VT-d)
> `= <boolean>`
+**WARNING: This command line option is deprecated, and superseded by
+_dom0-iommu=map-inclusive_ - using both options in combination is undefined.**
+
> Default: `true`
Use this to work around firmware issues providing incorrect RMRR entries.
diff --git a/xen/drivers/passthrough/amd/pci_amd_iommu.c b/xen/drivers/passthrough/amd/pci_amd_iommu.c
index ab39e7500d..073d18bd10 100644
--- a/xen/drivers/passthrough/amd/pci_amd_iommu.c
+++ b/xen/drivers/passthrough/amd/pci_amd_iommu.c
@@ -253,6 +253,10 @@ static void __hwdom_init amd_iommu_hwdom_init(struct domain *d)
unsigned long i;
const struct amd_iommu *iommu;
+ /* Inclusive IOMMU mappings are disabled by default on AMD hardware. */
+ if ( iommu_hwdom_inclusive == -1 )
+ iommu_hwdom_inclusive = 0;
+
if ( allocate_domain_resources(dom_iommu(d)) )
BUG();
diff --git a/xen/drivers/passthrough/arm/iommu.c b/xen/drivers/passthrough/arm/iommu.c
index 95b1abb972..325997b19f 100644
--- a/xen/drivers/passthrough/arm/iommu.c
+++ b/xen/drivers/passthrough/arm/iommu.c
@@ -73,3 +73,7 @@ int arch_iommu_populate_page_table(struct domain *d)
/* The IOMMU shares the p2m with the CPU */
return -ENOSYS;
}
+
+void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
+{
+}
diff --git a/xen/drivers/passthrough/arm/smmu.c b/xen/drivers/passthrough/arm/smmu.c
index 74c09b0991..a5158b0bdf 100644
--- a/xen/drivers/passthrough/arm/smmu.c
+++ b/xen/drivers/passthrough/arm/smmu.c
@@ -2727,6 +2727,11 @@ static int arm_smmu_iommu_domain_init(struct domain *d)
static void __hwdom_init arm_smmu_iommu_hwdom_init(struct domain *d)
{
+ /* Set to false options not supported on ARM. */
+ if ( iommu_hwdom_inclusive == 1 )
+ printk(XENLOG_WARNING
+ "map-inclusive dom0-iommu option is not supported on ARM\n");
+ iommu_hwdom_inclusive = 0;
}
static void arm_smmu_iommu_domain_teardown(struct domain *d)
diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index 8f9975cf4e..9552464bdc 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -61,6 +61,7 @@ bool_t __read_mostly iommu_intremap = 1;
bool __hwdom_initdata iommu_hwdom_strict;
bool __read_mostly iommu_hwdom_passthrough;
+int8_t __hwdom_initdata iommu_hwdom_inclusive = -1;
/*
* In the current implementation of VT-d posted interrupts, in some extreme
@@ -152,6 +153,8 @@ static int __init parse_dom0_iommu_param(const char *s)
iommu_hwdom_passthrough = val;
else if ( (val = parse_boolean("strict", s, ss)) >= 0 )
iommu_hwdom_strict = val;
+ else if ( (val = parse_boolean("map-inclusive", s, ss)) >= 0 )
+ iommu_hwdom_inclusive = val;
else
rc = -EINVAL;
@@ -232,6 +235,16 @@ void __hwdom_init iommu_hwdom_init(struct domain *d)
}
hd->platform_ops->hwdom_init(d);
+
+ ASSERT(iommu_hwdom_inclusive != -1);
+ if ( iommu_hwdom_inclusive && !is_pv_domain(d) )
+ {
+ printk(XENLOG_WARNING
+ "IOMMU inclusive mappings are only supported on PV Dom0\n");
+ iommu_hwdom_inclusive = 0;
+ }
+
+ arch_iommu_hwdom_init(d);
}
void iommu_teardown(struct domain *d)
diff --git a/xen/drivers/passthrough/vtd/extern.h b/xen/drivers/passthrough/vtd/extern.h
index fb7edfaef9..91cadc602e 100644
--- a/xen/drivers/passthrough/vtd/extern.h
+++ b/xen/drivers/passthrough/vtd/extern.h
@@ -99,6 +99,4 @@ void pci_vtd_quirk(const struct pci_dev *);
bool_t platform_supports_intremap(void);
bool_t platform_supports_x2apic(void);
-void vtd_set_hwdom_mapping(struct domain *d);
-
#endif // _VTD_EXTERN_H_
diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index 32bf0fc299..a09e02c8db 100644
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -1304,11 +1304,9 @@ static void __hwdom_init intel_iommu_hwdom_init(struct domain *d)
{
struct acpi_drhd_unit *drhd;
- if ( !iommu_hwdom_passthrough && is_pv_domain(d) )
- {
- /* Set up 1:1 page table for hardware domain. */
- vtd_set_hwdom_mapping(d);
- }
+ /* Inclusive mappings are enabled by default on Intel hardware for PV. */
+ if ( iommu_hwdom_inclusive == -1 )
+ iommu_hwdom_inclusive = is_pv_domain(d);
setup_hwdom_pci_devices(d, setup_hwdom_device);
setup_hwdom_rmrr(d);
diff --git a/xen/drivers/passthrough/vtd/x86/vtd.c b/xen/drivers/passthrough/vtd/x86/vtd.c
index ef1a02cba6..48e16f956b 100644
--- a/xen/drivers/passthrough/vtd/x86/vtd.c
+++ b/xen/drivers/passthrough/vtd/x86/vtd.c
@@ -25,7 +25,6 @@
#include <xen/irq.h>
#include <xen/numa.h>
#include <asm/fixmap.h>
-#include <asm/setup.h>
#include "../iommu.h"
#include "../dmar.h"
#include "../vtd.h"
@@ -35,8 +34,7 @@
* iommu_inclusive_mapping: when set, all memory below 4GB is included in dom0
* 1:1 iommu mappings except xen and unusable regions.
*/
-static bool_t __hwdom_initdata iommu_inclusive_mapping = 1;
-boolean_param("iommu_inclusive_mapping", iommu_inclusive_mapping);
+boolean_param("iommu_inclusive_mapping", iommu_hwdom_inclusive);
void *map_vtd_domain_page(u64 maddr)
{
@@ -63,57 +61,3 @@ void flush_all_cache()
wbinvd();
}
-void __hwdom_init vtd_set_hwdom_mapping(struct domain *d)
-{
- unsigned long i, top, max_pfn;
-
- BUG_ON(!is_hardware_domain(d));
-
- max_pfn = (GB(4) >> PAGE_SHIFT) - 1;
- top = max(max_pdx, pfn_to_pdx(max_pfn) + 1);
-
- for ( i = 0; i < top; i++ )
- {
- unsigned long pfn = pdx_to_pfn(i);
- bool map;
- int rc;
-
- /*
- * Set up 1:1 mapping for dom0. Default to include only
- * conventional RAM areas and let RMRRs include needed reserved
- * regions. When set, the inclusive mapping additionally maps in
- * every pfn up to 4GB except those that fall in unusable ranges.
- */
- if ( pfn > max_pfn && !mfn_valid(_mfn(pfn)) )
- continue;
-
- if ( iommu_inclusive_mapping && pfn <= max_pfn )
- map = !page_is_ram_type(pfn, RAM_TYPE_UNUSABLE);
- else
- map = page_is_ram_type(pfn, RAM_TYPE_CONVENTIONAL);
-
- if ( !map )
- continue;
-
- /* Exclude Xen bits */
- if ( xen_in_range(pfn) )
- continue;
-
- /*
- * If dom0-strict mode is enabled then exclude conventional RAM
- * and let the common code map dom0's pages.
- */
- if ( iommu_hwdom_strict &&
- page_is_ram_type(pfn, RAM_TYPE_CONVENTIONAL) )
- continue;
-
- rc = iommu_map_page(d, pfn, pfn, IOMMUF_readable|IOMMUF_writable);
- if ( rc )
- printk(XENLOG_WARNING VTDPREFIX " d%d: IOMMU mapping failed: %d\n",
- d->domain_id, rc);
-
- if (!(i & 0xfffff))
- process_pending_softirqs();
- }
-}
-
diff --git a/xen/drivers/passthrough/x86/iommu.c b/xen/drivers/passthrough/x86/iommu.c
index 68182afd91..25e1ebf8b3 100644
--- a/xen/drivers/passthrough/x86/iommu.c
+++ b/xen/drivers/passthrough/x86/iommu.c
@@ -20,6 +20,8 @@
#include <xen/softirq.h>
#include <xsm/xsm.h>
+#include <asm/setup.h>
+
void iommu_update_ire_from_apic(
unsigned int apic, unsigned int reg, unsigned int value)
{
@@ -132,6 +134,63 @@ void arch_iommu_domain_destroy(struct domain *d)
{
}
+void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
+{
+ unsigned long i, top, max_pfn;
+
+ BUG_ON(!is_hardware_domain(d));
+
+ if ( iommu_hwdom_passthrough || !is_pv_domain(d) )
+ return;
+
+ max_pfn = (GB(4) >> PAGE_SHIFT) - 1;
+ top = max(max_pdx, pfn_to_pdx(max_pfn) + 1);
+
+ for ( i = 0; i < top; i++ )
+ {
+ unsigned long pfn = pdx_to_pfn(i);
+ bool map;
+ int rc;
+
+ /*
+ * Set up 1:1 mapping for dom0. Default to include only
+ * conventional RAM areas and let RMRRs include needed reserved
+ * regions. When set, the inclusive mapping additionally maps in
+ * every pfn up to 4GB except those that fall in unusable ranges.
+ */
+ if ( pfn > max_pfn && !mfn_valid(_mfn(pfn)) )
+ continue;
+
+ if ( iommu_hwdom_inclusive && pfn <= max_pfn )
+ map = !page_is_ram_type(pfn, RAM_TYPE_UNUSABLE);
+ else
+ map = page_is_ram_type(pfn, RAM_TYPE_CONVENTIONAL);
+
+ if ( !map )
+ continue;
+
+ /* Exclude Xen bits */
+ if ( xen_in_range(pfn) )
+ continue;
+
+ /*
+ * If dom0-strict mode is enabled then exclude conventional RAM
+ * and let the common code map dom0's pages.
+ */
+ if ( iommu_hwdom_strict &&
+ page_is_ram_type(pfn, RAM_TYPE_CONVENTIONAL) )
+ continue;
+
+ rc = iommu_map_page(d, pfn, pfn, IOMMUF_readable|IOMMUF_writable);
+ if ( rc )
+ printk(XENLOG_WARNING " d%d: IOMMU mapping failed: %d\n",
+ d->domain_id, rc);
+
+ if (!(i & 0xfffff))
+ process_pending_softirqs();
+ }
+}
+
/*
* Local variables:
* mode: C
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index 392cf1e6b9..89c6830689 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -37,6 +37,7 @@ extern bool_t iommu_debug;
extern bool_t amd_iommu_perdev_intremap;
extern bool iommu_hwdom_strict, iommu_hwdom_passthrough;
+extern int8_t iommu_hwdom_inclusive;
extern unsigned int iommu_dev_iotlb_timeout;
@@ -51,6 +52,7 @@ void arch_iommu_domain_destroy(struct domain *d);
int arch_iommu_domain_init(struct domain *d);
int arch_iommu_populate_page_table(struct domain *d);
void arch_iommu_check_autotranslated_hwdom(struct domain *d);
+void arch_iommu_hwdom_init(struct domain *d);
int iommu_construct(struct domain *d);
--
2.18.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 14+ messages in thread* Re: [PATCH v8 3/6] iommu: make iommu_inclusive_mapping a suboption of dom0-iommu
2018-09-07 9:07 ` [PATCH v8 3/6] iommu: make iommu_inclusive_mapping a suboption of dom0-iommu Roger Pau Monne
@ 2018-09-10 11:30 ` Julien Grall
2018-09-12 11:59 ` Suravee Suthikulpanit
1 sibling, 0 replies; 14+ messages in thread
From: Julien Grall @ 2018-09-10 11:30 UTC (permalink / raw)
To: Roger Pau Monne, xen-devel
Cc: Kevin Tian, Stefano Stabellini, Wei Liu, Suravee Suthikulpanit,
Konrad Rzeszutek Wilk, George Dunlap, Andrew Cooper, Ian Jackson,
Tim Deegan, Jan Beulich, Brian Woods
Hi Roger,
On 07/09/18 10:07, Roger Pau Monne wrote:
> Introduce a new dom0-iommu=map-inclusive generic option that
> supersedes iommu_inclusive_mapping. The previous behavior is preserved
> and the option should only be enabled by default on Intel hardware.
>
> Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
> Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
> Reviewed-by: Jan Beulich <jbeulich@suse.com>
> Reviewed-by: Kevin Tian <kevin.tian@intel.com>
For Arm:
Acked-by: Julien Grall <julien.grall@arm.com>
Cheers,
--
Julien Grall
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH v8 3/6] iommu: make iommu_inclusive_mapping a suboption of dom0-iommu
2018-09-07 9:07 ` [PATCH v8 3/6] iommu: make iommu_inclusive_mapping a suboption of dom0-iommu Roger Pau Monne
2018-09-10 11:30 ` Julien Grall
@ 2018-09-12 11:59 ` Suravee Suthikulpanit
1 sibling, 0 replies; 14+ messages in thread
From: Suravee Suthikulpanit @ 2018-09-12 11:59 UTC (permalink / raw)
To: Roger Pau Monne, xen-devel
Cc: Kevin Tian, Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk,
George Dunlap, Andrew Cooper, Ian Jackson, Tim Deegan,
Julien Grall, Jan Beulich, Brian Woods
On 9/7/18 4:07 PM, Roger Pau Monne wrote:
> Introduce a new dom0-iommu=map-inclusive generic option that
> supersedes iommu_inclusive_mapping. The previous behavior is preserved
> and the option should only be enabled by default on Intel hardware.
>
> Signed-off-by: Roger Pau Monné<roger.pau@citrix.com>
> Reviewed-by: Paul Durrant<paul.durrant@citrix.com>
> Reviewed-by: Jan Beulich<jbeulich@suse.com>
> Reviewed-by: Kevin Tian<kevin.tian@intel.com>
> ---
> Changes since v7:
> - Use -1, 0, 1 in iommu_hwdom_inclusive.
> - Print a warning message if map-inclusive is set on ARM.
>
> Changes since v4:
> - Use an if to set the default option value.
> - Set the option to false unconditionally on ARM.
>
> Changes since v2:
> - Fix typo in commit message.
> - Change style and text of the documentation in xen command line.
> - Set the defaults in {intel/amd}_iommu_hwdom_init for inclusive.
> - Re-add the iommu_dom0_passthrough || !is_pv_domain(d) check.
>
> Changes since v1:
> - Use dom0-iommu instead of the iommu option.
> - Only enable by default on Intel hardware.
> ---
> Cc: Andrew Cooper<andrew.cooper3@citrix.com>
> Cc: George Dunlap<George.Dunlap@eu.citrix.com>
> Cc: Ian Jackson<ian.jackson@eu.citrix.com>
> Cc: Jan Beulich<jbeulich@suse.com>
> Cc: Julien Grall<julien.grall@arm.com>
> Cc: Konrad Rzeszutek Wilk<konrad.wilk@oracle.com>
> Cc: Stefano Stabellini<sstabellini@kernel.org>
> Cc: Tim Deegan<tim@xen.org>
> Cc: Wei Liu<wei.liu2@citrix.com>
> Cc: Suravee Suthikulpanit<suravee.suthikulpanit@amd.com>
> Cc: Brian Woods<brian.woods@amd.com>
> Cc: Kevin Tian<kevin.tian@intel.com>
For AMD-related changes.
Acked-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Thank you,
Suravee
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 14+ messages in thread
* [PATCH v8 4/6] mm: introduce a helper to get the memory type of a page
2018-09-07 9:07 [PATCH v8 0/6] x86/iommu: PVH Dom0 workarounds for missing RMRR entries Roger Pau Monne
` (2 preceding siblings ...)
2018-09-07 9:07 ` [PATCH v8 3/6] iommu: make iommu_inclusive_mapping a suboption of dom0-iommu Roger Pau Monne
@ 2018-09-07 9:07 ` Roger Pau Monne
2018-09-07 9:07 ` [PATCH v8 5/6] x86/iommu: switch the hwdom mapping function to use page_get_type Roger Pau Monne
2018-09-07 9:07 ` [PATCH v8 6/6] x86/iommu: add map-reserved dom0-iommu option to map reserved memory ranges Roger Pau Monne
5 siblings, 0 replies; 14+ messages in thread
From: Roger Pau Monne @ 2018-09-07 9:07 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk, George Dunlap,
Andrew Cooper, Ian Jackson, Tim Deegan, Julien Grall, Jan Beulich,
Roger Pau Monne
Returns all the memory types applicable to a page.
This function is unimplemented for ARM.
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
---
Changes since v7:
- Switch the parameter type to mfn_t.
Changes since v5:
- Return all types that apply to a page, since the types themselves
are flags that can be or'ed together.
---
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Julien Grall <julien.grall@arm.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Tim Deegan <tim@xen.org>
Cc: Wei Liu <wei.liu2@citrix.com>
---
xen/arch/x86/mm.c | 42 ++++++++++++++++++++++++++++++++++++++++++
xen/include/xen/mm.h | 3 +++
2 files changed, 45 insertions(+)
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index baea2f5e63..d37eea53d1 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -430,6 +430,48 @@ int page_is_ram_type(unsigned long mfn, unsigned long mem_type)
return 0;
}
+unsigned int page_get_ram_type(mfn_t mfn)
+{
+ uint64_t last = 0, maddr = mfn_to_maddr(mfn);
+ unsigned int i, type = 0;
+
+ for ( i = 0; i < e820.nr_map;
+ last = e820.map[i].addr + e820.map[i].size, i++ )
+ {
+ if ( (maddr + PAGE_SIZE) > last && maddr < e820.map[i].addr )
+ type |= RAM_TYPE_UNKNOWN;
+
+ if ( (maddr + PAGE_SIZE) <= e820.map[i].addr ||
+ maddr >= (e820.map[i].addr + e820.map[i].size) )
+ continue;
+
+ switch ( e820.map[i].type )
+ {
+ case E820_RAM:
+ type |= RAM_TYPE_CONVENTIONAL;
+ break;
+
+ case E820_RESERVED:
+ type |= RAM_TYPE_RESERVED;
+ break;
+
+ case E820_UNUSABLE:
+ type |= RAM_TYPE_UNUSABLE;
+ break;
+
+ case E820_ACPI:
+ case E820_NVS:
+ type |= RAM_TYPE_ACPI;
+ break;
+
+ default:
+ ASSERT_UNREACHABLE();
+ }
+ }
+
+ return type ?: RAM_TYPE_UNKNOWN;
+}
+
unsigned long domain_get_maximum_gpfn(struct domain *d)
{
if ( is_hvm_domain(d) )
diff --git a/xen/include/xen/mm.h b/xen/include/xen/mm.h
index 24654e8e22..b3d46ab56b 100644
--- a/xen/include/xen/mm.h
+++ b/xen/include/xen/mm.h
@@ -595,8 +595,11 @@ int __must_check donate_page(struct domain *d, struct page_info *page,
#define RAM_TYPE_RESERVED 0x00000002
#define RAM_TYPE_UNUSABLE 0x00000004
#define RAM_TYPE_ACPI 0x00000008
+#define RAM_TYPE_UNKNOWN 0x00000010
/* TRUE if the whole page at @mfn is of the requested RAM type(s) above. */
int page_is_ram_type(unsigned long mfn, unsigned long mem_type);
+/* Returns the page type(s). */
+unsigned int page_get_ram_type(mfn_t mfn);
/* Prepare/destroy a ring for a dom0 helper. Helper with talk
* with Xen on behalf of this domain. */
--
2.18.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v8 5/6] x86/iommu: switch the hwdom mapping function to use page_get_type
2018-09-07 9:07 [PATCH v8 0/6] x86/iommu: PVH Dom0 workarounds for missing RMRR entries Roger Pau Monne
` (3 preceding siblings ...)
2018-09-07 9:07 ` [PATCH v8 4/6] mm: introduce a helper to get the memory type of a page Roger Pau Monne
@ 2018-09-07 9:07 ` Roger Pau Monne
2018-09-07 9:07 ` [PATCH v8 6/6] x86/iommu: add map-reserved dom0-iommu option to map reserved memory ranges Roger Pau Monne
5 siblings, 0 replies; 14+ messages in thread
From: Roger Pau Monne @ 2018-09-07 9:07 UTC (permalink / raw)
To: xen-devel; +Cc: Jan Beulich, Roger Pau Monne
This avoids repeated calls to page_is_ram_type which improves
performance and makes the code easier to read.
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Wei Liu <wei.liu2@citrix.com>
---
Changes since v7:
- Switch to use mfn_t with page_get_ram_type.
Changes since v4:
- New in this version.
---
Cc: Jan Beulich <jbeulich@suse.com>
---
xen/drivers/passthrough/x86/iommu.c | 62 ++++++++++++++++-------------
1 file changed, 34 insertions(+), 28 deletions(-)
diff --git a/xen/drivers/passthrough/x86/iommu.c b/xen/drivers/passthrough/x86/iommu.c
index 25e1ebf8b3..5809027573 100644
--- a/xen/drivers/passthrough/x86/iommu.c
+++ b/xen/drivers/passthrough/x86/iommu.c
@@ -134,6 +134,39 @@ void arch_iommu_domain_destroy(struct domain *d)
{
}
+static bool __hwdom_init hwdom_iommu_map(const struct domain *d,
+ unsigned long pfn,
+ unsigned long max_pfn)
+{
+ mfn_t mfn = _mfn(pfn);
+
+ /*
+ * Set up 1:1 mapping for dom0. Default to include only conventional RAM
+ * areas and let RMRRs include needed reserved regions. When set, the
+ * inclusive mapping additionally maps in every pfn up to 4GB except those
+ * that fall in unusable ranges.
+ */
+ if ( (pfn > max_pfn && !mfn_valid(mfn)) || xen_in_range(pfn) )
+ return false;
+
+ switch ( page_get_ram_type(mfn) )
+ {
+ case RAM_TYPE_UNUSABLE:
+ return false;
+
+ case RAM_TYPE_CONVENTIONAL:
+ if ( iommu_hwdom_strict )
+ return false;
+ break;
+
+ default:
+ if ( !iommu_hwdom_inclusive || pfn > max_pfn )
+ return false;
+ }
+
+ return true;
+}
+
void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
{
unsigned long i, top, max_pfn;
@@ -149,36 +182,9 @@ void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
for ( i = 0; i < top; i++ )
{
unsigned long pfn = pdx_to_pfn(i);
- bool map;
int rc;
- /*
- * Set up 1:1 mapping for dom0. Default to include only
- * conventional RAM areas and let RMRRs include needed reserved
- * regions. When set, the inclusive mapping additionally maps in
- * every pfn up to 4GB except those that fall in unusable ranges.
- */
- if ( pfn > max_pfn && !mfn_valid(_mfn(pfn)) )
- continue;
-
- if ( iommu_hwdom_inclusive && pfn <= max_pfn )
- map = !page_is_ram_type(pfn, RAM_TYPE_UNUSABLE);
- else
- map = page_is_ram_type(pfn, RAM_TYPE_CONVENTIONAL);
-
- if ( !map )
- continue;
-
- /* Exclude Xen bits */
- if ( xen_in_range(pfn) )
- continue;
-
- /*
- * If dom0-strict mode is enabled then exclude conventional RAM
- * and let the common code map dom0's pages.
- */
- if ( iommu_hwdom_strict &&
- page_is_ram_type(pfn, RAM_TYPE_CONVENTIONAL) )
+ if ( !hwdom_iommu_map(d, pfn, max_pfn) )
continue;
rc = iommu_map_page(d, pfn, pfn, IOMMUF_readable|IOMMUF_writable);
--
2.18.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v8 6/6] x86/iommu: add map-reserved dom0-iommu option to map reserved memory ranges
2018-09-07 9:07 [PATCH v8 0/6] x86/iommu: PVH Dom0 workarounds for missing RMRR entries Roger Pau Monne
` (4 preceding siblings ...)
2018-09-07 9:07 ` [PATCH v8 5/6] x86/iommu: switch the hwdom mapping function to use page_get_type Roger Pau Monne
@ 2018-09-07 9:07 ` Roger Pau Monne
2018-09-10 11:31 ` Julien Grall
` (2 more replies)
5 siblings, 3 replies; 14+ messages in thread
From: Roger Pau Monne @ 2018-09-07 9:07 UTC (permalink / raw)
To: xen-devel
Cc: Kevin Tian, Stefano Stabellini, Wei Liu, Suravee Suthikulpanit,
Konrad Rzeszutek Wilk, George Dunlap, Andrew Cooper, Ian Jackson,
Tim Deegan, Julien Grall, Paul Durrant, Jan Beulich, Brian Woods,
Roger Pau Monne
Several people have reported hardware issues (malfunctioning USB
controllers) due to iommu page faults on Intel hardware. Those faults
are caused by missing RMRR (VTd) entries in the ACPI tables. Those can
be worked around on VTd hardware by manually adding RMRR entries on
the command line, this is however limited to Intel hardware and quite
cumbersome to do.
In order to solve those issues add a new dom0-iommu=map-reserved
option that identity maps all regions marked as reserved in the memory
map. Note that regions used by devices emulated by Xen (LAPIC, IO-APIC
or PCIe MCFG regions) are specifically avoided. Note that this option
is available to all Dom0 modes (as opposed to the inclusive option
which only works for PV Dom0).
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
---
Changes since v7:
- Don't use true/false with int8_t.
- Print a warning message if map-reserved is set on ARM.
Changes since v6:
- Reword the map-reserved help to make it clear it's available to
both PV and PVH Dom0.
- Assign type inside of the switch expression.
- Remove the comment about IO-APIC MMIO relocation, this is not
supported ATM.
Changes since v5:
- Merge with the vpci MMCFG helper patch.
- Add a TODO item about the issues with relocating the LAPIC or
IOAPIC MMIO regions.
- Use the newly introduced page_get_ram_type that returns all the
types that fall between a page.
- Use paging_mode_translate instead of iommu_use_hap_pt when deciding
whether to use set_identity_p2m_entry or iommu_map_page.
Changes since v4:
- Use pfn_to_paddr.
- Rebase on top of previous changes.
- Change the default option setting to use if instead of a ternary
operator.
- Rename to map-reserved.
Changes since v3:
- Add mappings if the iommu page tables are shared.
Changes since v2:
- Fix comment regarding dom0-strict.
- Change documentation style of xen command line.
- Rename iommu_map to hwdom_iommu_map.
- Move all the checks to hwdom_iommu_map.
Changes since v1:
- Introduce a new reserved option instead of abusing the inclusive
option.
- Use the same helper function for PV and PVH in order to decide if a
page should be added to the domain page tables.
- Use the data inside of the domain struct to detect overlaps with
emulated MMIO regions.
---
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Julien Grall <julien.grall@arm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tim Deegan <tim@xen.org>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Paul Durrant <paul.durrant@citrix.com>
Cc: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Cc: Brian Woods <brian.woods@amd.com>
Cc: Kevin Tian <kevin.tian@intel.com>
---
docs/misc/xen-command-line.markdown | 9 ++++
xen/arch/x86/hvm/io.c | 5 ++
xen/drivers/passthrough/amd/pci_amd_iommu.c | 3 ++
xen/drivers/passthrough/arm/smmu.c | 4 ++
xen/drivers/passthrough/iommu.c | 5 +-
xen/drivers/passthrough/vtd/iommu.c | 3 ++
xen/drivers/passthrough/x86/iommu.c | 52 ++++++++++++++++++---
xen/include/asm-x86/hvm/io.h | 3 ++
xen/include/xen/iommu.h | 2 +-
9 files changed, 78 insertions(+), 8 deletions(-)
diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown
index 98f0f3b68b..1ffd586224 100644
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -704,6 +704,15 @@ This list of booleans controls the iommu usage by Dom0:
option is only applicable to a PV Dom0 and is enabled by default on Intel
hardware.
+* `map-reserved`: sets up DMA remapping for all the reserved regions in the
+ memory map for Dom0. Use this to work around firmware issues providing
+ incorrect RMRR/IVMD entries. Rather than only mapping RAM pages for IOMMU
+ accesses for Dom0, all memory regions marked as reserved in the memory map
+ that don't overlap with any MMIO region from emulated devices will be
+ identity mapped. This option maps a subset of the memory that would be
+ mapped when using the `map-inclusive` option. This option is available to all
+ Dom0 modes and is enabled by default on Intel hardware.
+
### dom0\_ioports\_disable (x86)
> `= List of <hex>-<hex>`
diff --git a/xen/arch/x86/hvm/io.c b/xen/arch/x86/hvm/io.c
index 47d6c850ca..a5b0a23f06 100644
--- a/xen/arch/x86/hvm/io.c
+++ b/xen/arch/x86/hvm/io.c
@@ -404,6 +404,11 @@ static const struct hvm_mmcfg *vpci_mmcfg_find(const struct domain *d,
return NULL;
}
+bool vpci_is_mmcfg_address(const struct domain *d, paddr_t addr)
+{
+ return vpci_mmcfg_find(d, addr);
+}
+
static unsigned int vpci_mmcfg_decode_addr(const struct hvm_mmcfg *mmcfg,
paddr_t addr, pci_sbdf_t *sbdf)
{
diff --git a/xen/drivers/passthrough/amd/pci_amd_iommu.c b/xen/drivers/passthrough/amd/pci_amd_iommu.c
index 073d18bd10..330f9ce386 100644
--- a/xen/drivers/passthrough/amd/pci_amd_iommu.c
+++ b/xen/drivers/passthrough/amd/pci_amd_iommu.c
@@ -256,6 +256,9 @@ static void __hwdom_init amd_iommu_hwdom_init(struct domain *d)
/* Inclusive IOMMU mappings are disabled by default on AMD hardware. */
if ( iommu_hwdom_inclusive == -1 )
iommu_hwdom_inclusive = 0;
+ /* Reserved IOMMU mappings are disabled by default on AMD hardware. */
+ if ( iommu_hwdom_reserved == -1 )
+ iommu_hwdom_reserved = 0;
if ( allocate_domain_resources(dom_iommu(d)) )
BUG();
diff --git a/xen/drivers/passthrough/arm/smmu.c b/xen/drivers/passthrough/arm/smmu.c
index a5158b0bdf..43ece42a50 100644
--- a/xen/drivers/passthrough/arm/smmu.c
+++ b/xen/drivers/passthrough/arm/smmu.c
@@ -2732,6 +2732,10 @@ static void __hwdom_init arm_smmu_iommu_hwdom_init(struct domain *d)
printk(XENLOG_WARNING
"map-inclusive dom0-iommu option is not supported on ARM\n");
iommu_hwdom_inclusive = 0;
+ if ( iommu_hwdom_reserved == 1 )
+ printk(XENLOG_WARNING
+ "map-reserved dom0-iommu option is not supported on ARM\n");
+ iommu_hwdom_reserved = 0;
}
static void arm_smmu_iommu_domain_teardown(struct domain *d)
diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index 9552464bdc..a29bc13f8a 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -62,6 +62,7 @@ bool_t __read_mostly iommu_intremap = 1;
bool __hwdom_initdata iommu_hwdom_strict;
bool __read_mostly iommu_hwdom_passthrough;
int8_t __hwdom_initdata iommu_hwdom_inclusive = -1;
+int8_t __hwdom_initdata iommu_hwdom_reserved = -1;
/*
* In the current implementation of VT-d posted interrupts, in some extreme
@@ -155,6 +156,8 @@ static int __init parse_dom0_iommu_param(const char *s)
iommu_hwdom_strict = val;
else if ( (val = parse_boolean("map-inclusive", s, ss)) >= 0 )
iommu_hwdom_inclusive = val;
+ else if ( (val = parse_boolean("map-reserved", s, ss)) >= 0 )
+ iommu_hwdom_inclusive = val;
else
rc = -EINVAL;
@@ -236,7 +239,7 @@ void __hwdom_init iommu_hwdom_init(struct domain *d)
hd->platform_ops->hwdom_init(d);
- ASSERT(iommu_hwdom_inclusive != -1);
+ ASSERT(iommu_hwdom_inclusive != -1 && iommu_hwdom_inclusive != -1);
if ( iommu_hwdom_inclusive && !is_pv_domain(d) )
{
printk(XENLOG_WARNING
diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index a09e02c8db..1121f5ff5b 100644
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -1307,6 +1307,9 @@ static void __hwdom_init intel_iommu_hwdom_init(struct domain *d)
/* Inclusive mappings are enabled by default on Intel hardware for PV. */
if ( iommu_hwdom_inclusive == -1 )
iommu_hwdom_inclusive = is_pv_domain(d);
+ /* Reserved IOMMU mappings are enabled by default on Intel hardware. */
+ if ( iommu_hwdom_reserved == -1 )
+ iommu_hwdom_reserved = 1;
setup_hwdom_pci_devices(d, setup_hwdom_device);
setup_hwdom_rmrr(d);
diff --git a/xen/drivers/passthrough/x86/iommu.c b/xen/drivers/passthrough/x86/iommu.c
index 5809027573..47a078272a 100644
--- a/xen/drivers/passthrough/x86/iommu.c
+++ b/xen/drivers/passthrough/x86/iommu.c
@@ -20,6 +20,7 @@
#include <xen/softirq.h>
#include <xsm/xsm.h>
+#include <asm/hvm/io.h>
#include <asm/setup.h>
void iommu_update_ire_from_apic(
@@ -139,17 +140,23 @@ static bool __hwdom_init hwdom_iommu_map(const struct domain *d,
unsigned long max_pfn)
{
mfn_t mfn = _mfn(pfn);
+ unsigned int i, type;
/*
* Set up 1:1 mapping for dom0. Default to include only conventional RAM
* areas and let RMRRs include needed reserved regions. When set, the
* inclusive mapping additionally maps in every pfn up to 4GB except those
- * that fall in unusable ranges.
+ * that fall in unusable ranges for PV Dom0.
*/
- if ( (pfn > max_pfn && !mfn_valid(mfn)) || xen_in_range(pfn) )
+ if ( (pfn > max_pfn && !mfn_valid(mfn)) || xen_in_range(pfn) ||
+ /*
+ * Ignore any address below 1MB, that's already identity mapped by the
+ * Dom0 builder for HVM.
+ */
+ (!d->domain_id && is_hvm_domain(d) && pfn < PFN_DOWN(MB(1))) )
return false;
- switch ( page_get_ram_type(mfn) )
+ switch ( type = page_get_ram_type(mfn) )
{
case RAM_TYPE_UNUSABLE:
return false;
@@ -160,10 +167,40 @@ static bool __hwdom_init hwdom_iommu_map(const struct domain *d,
break;
default:
- if ( !iommu_hwdom_inclusive || pfn > max_pfn )
+ if ( type & RAM_TYPE_RESERVED )
+ {
+ if ( !iommu_hwdom_inclusive && !iommu_hwdom_reserved )
+ return false;
+ }
+ else if ( is_hvm_domain(d) || !iommu_hwdom_inclusive || pfn > max_pfn )
return false;
}
+ /*
+ * Check that it doesn't overlap with the LAPIC
+ * TODO: if the guest relocates the MMIO area of the LAPIC Xen should make
+ * sure there's nothing in the new address that would prevent trapping.
+ */
+ if ( has_vlapic(d) )
+ {
+ const struct vcpu *v;
+
+ for_each_vcpu(d, v)
+ if ( pfn == PFN_DOWN(vlapic_base_address(vcpu_vlapic(v))) )
+ return false;
+ }
+ /* ... or the IO-APIC */
+ for ( i = 0; has_vioapic(d) && i < d->arch.hvm.nr_vioapics; i++ )
+ if ( pfn == PFN_DOWN(domain_vioapic(d, i)->base_address) )
+ return false;
+ /*
+ * ... or the PCIe MCFG regions.
+ * TODO: runtime added MMCFG regions are not checked to make sure they
+ * don't overlap with already mapped regions, thus preventing trapping.
+ */
+ if ( has_vpci(d) && vpci_is_mmcfg_address(d, pfn_to_paddr(pfn)) )
+ return false;
+
return true;
}
@@ -173,7 +210,7 @@ void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
BUG_ON(!is_hardware_domain(d));
- if ( iommu_hwdom_passthrough || !is_pv_domain(d) )
+ if ( iommu_hwdom_passthrough )
return;
max_pfn = (GB(4) >> PAGE_SHIFT) - 1;
@@ -187,7 +224,10 @@ void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
if ( !hwdom_iommu_map(d, pfn, max_pfn) )
continue;
- rc = iommu_map_page(d, pfn, pfn, IOMMUF_readable|IOMMUF_writable);
+ if ( paging_mode_translate(d) )
+ rc = set_identity_p2m_entry(d, pfn, p2m_access_rw, 0);
+ else
+ rc = iommu_map_page(d, pfn, pfn, IOMMUF_readable|IOMMUF_writable);
if ( rc )
printk(XENLOG_WARNING " d%d: IOMMU mapping failed: %d\n",
d->domain_id, rc);
diff --git a/xen/include/asm-x86/hvm/io.h b/xen/include/asm-x86/hvm/io.h
index 8c83fd0c8b..7ceb119b64 100644
--- a/xen/include/asm-x86/hvm/io.h
+++ b/xen/include/asm-x86/hvm/io.h
@@ -185,6 +185,9 @@ int register_vpci_mmcfg_handler(struct domain *d, paddr_t addr,
/* Destroy tracked MMCFG areas. */
void destroy_vpci_mmcfg(struct domain *d);
+/* Check if an address is between a MMCFG region for a domain. */
+bool vpci_is_mmcfg_address(const struct domain *d, paddr_t addr);
+
#endif /* __ASM_X86_HVM_IO_H__ */
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index 89c6830689..57c4e81ec6 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -37,7 +37,7 @@ extern bool_t iommu_debug;
extern bool_t amd_iommu_perdev_intremap;
extern bool iommu_hwdom_strict, iommu_hwdom_passthrough;
-extern int8_t iommu_hwdom_inclusive;
+extern int8_t iommu_hwdom_inclusive, iommu_hwdom_reserved;
extern unsigned int iommu_dev_iotlb_timeout;
--
2.18.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 14+ messages in thread* Re: [PATCH v8 6/6] x86/iommu: add map-reserved dom0-iommu option to map reserved memory ranges
2018-09-07 9:07 ` [PATCH v8 6/6] x86/iommu: add map-reserved dom0-iommu option to map reserved memory ranges Roger Pau Monne
@ 2018-09-10 11:31 ` Julien Grall
2018-09-11 7:50 ` Paul Durrant
2018-09-12 11:59 ` Suravee Suthikulpanit
2 siblings, 0 replies; 14+ messages in thread
From: Julien Grall @ 2018-09-10 11:31 UTC (permalink / raw)
To: Roger Pau Monne, xen-devel
Cc: Kevin Tian, Stefano Stabellini, Wei Liu, Suravee Suthikulpanit,
Konrad Rzeszutek Wilk, George Dunlap, Andrew Cooper, Ian Jackson,
Tim Deegan, Paul Durrant, Jan Beulich, Brian Woods
Hi Roger,
On 07/09/18 10:07, Roger Pau Monne wrote:
> Several people have reported hardware issues (malfunctioning USB
> controllers) due to iommu page faults on Intel hardware. Those faults
> are caused by missing RMRR (VTd) entries in the ACPI tables. Those can
> be worked around on VTd hardware by manually adding RMRR entries on
> the command line, this is however limited to Intel hardware and quite
> cumbersome to do.
>
> In order to solve those issues add a new dom0-iommu=map-reserved
> option that identity maps all regions marked as reserved in the memory
> map. Note that regions used by devices emulated by Xen (LAPIC, IO-APIC
> or PCIe MCFG regions) are specifically avoided. Note that this option
> is available to all Dom0 modes (as opposed to the inclusive option
> which only works for PV Dom0).
>
> Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
> Reviewed-by: Kevin Tian <kevin.tian@intel.com>
> Reviewed-by: Wei Liu <wei.liu2@citrix.com>
> Acked-by: Jan Beulich <jbeulich@suse.com>
For Arm bits:
Acked-by: Julien Grall <julien.grall@arm.com>
Cheers,
--
Julien Grall
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH v8 6/6] x86/iommu: add map-reserved dom0-iommu option to map reserved memory ranges
2018-09-07 9:07 ` [PATCH v8 6/6] x86/iommu: add map-reserved dom0-iommu option to map reserved memory ranges Roger Pau Monne
2018-09-10 11:31 ` Julien Grall
@ 2018-09-11 7:50 ` Paul Durrant
2018-09-12 11:59 ` Suravee Suthikulpanit
2 siblings, 0 replies; 14+ messages in thread
From: Paul Durrant @ 2018-09-11 7:50 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Kevin Tian, Stefano Stabellini, Wei Liu, Suravee Suthikulpanit,
Konrad Rzeszutek Wilk, Andrew Cooper, Tim (Xen.org),
George Dunlap, Julien Grall, Jan Beulich, Ian Jackson,
Brian Woods, Roger Pau Monne
> -----Original Message-----
> From: Roger Pau Monne [mailto:roger.pau@citrix.com]
> Sent: 07 September 2018 10:08
> To: xen-devel@lists.xenproject.org
> Cc: Roger Pau Monne <roger.pau@citrix.com>; Andrew Cooper
> <Andrew.Cooper3@citrix.com>; George Dunlap
> <George.Dunlap@citrix.com>; Ian Jackson <Ian.Jackson@citrix.com>; Jan
> Beulich <jbeulich@suse.com>; Julien Grall <julien.grall@arm.com>; Konrad
> Rzeszutek Wilk <konrad.wilk@oracle.com>; Stefano Stabellini
> <sstabellini@kernel.org>; Tim (Xen.org) <tim@xen.org>; Wei Liu
> <wei.liu2@citrix.com>; Paul Durrant <Paul.Durrant@citrix.com>; Suravee
> Suthikulpanit <suravee.suthikulpanit@amd.com>; Brian Woods
> <brian.woods@amd.com>; Kevin Tian <kevin.tian@intel.com>
> Subject: [PATCH v8 6/6] x86/iommu: add map-reserved dom0-iommu option
> to map reserved memory ranges
>
> Several people have reported hardware issues (malfunctioning USB
> controllers) due to iommu page faults on Intel hardware. Those faults
> are caused by missing RMRR (VTd) entries in the ACPI tables. Those can
> be worked around on VTd hardware by manually adding RMRR entries on
> the command line, this is however limited to Intel hardware and quite
> cumbersome to do.
>
> In order to solve those issues add a new dom0-iommu=map-reserved
> option that identity maps all regions marked as reserved in the memory
> map. Note that regions used by devices emulated by Xen (LAPIC, IO-APIC
> or PCIe MCFG regions) are specifically avoided. Note that this option
> is available to all Dom0 modes (as opposed to the inclusive option
> which only works for PV Dom0).
>
> Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
> Reviewed-by: Kevin Tian <kevin.tian@intel.com>
> Reviewed-by: Wei Liu <wei.liu2@citrix.com>
> Acked-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
> ---
> Changes since v7:
> - Don't use true/false with int8_t.
> - Print a warning message if map-reserved is set on ARM.
>
> Changes since v6:
> - Reword the map-reserved help to make it clear it's available to
> both PV and PVH Dom0.
> - Assign type inside of the switch expression.
> - Remove the comment about IO-APIC MMIO relocation, this is not
> supported ATM.
>
> Changes since v5:
> - Merge with the vpci MMCFG helper patch.
> - Add a TODO item about the issues with relocating the LAPIC or
> IOAPIC MMIO regions.
> - Use the newly introduced page_get_ram_type that returns all the
> types that fall between a page.
> - Use paging_mode_translate instead of iommu_use_hap_pt when deciding
> whether to use set_identity_p2m_entry or iommu_map_page.
>
> Changes since v4:
> - Use pfn_to_paddr.
> - Rebase on top of previous changes.
> - Change the default option setting to use if instead of a ternary
> operator.
> - Rename to map-reserved.
>
> Changes since v3:
> - Add mappings if the iommu page tables are shared.
>
> Changes since v2:
> - Fix comment regarding dom0-strict.
> - Change documentation style of xen command line.
> - Rename iommu_map to hwdom_iommu_map.
> - Move all the checks to hwdom_iommu_map.
>
> Changes since v1:
> - Introduce a new reserved option instead of abusing the inclusive
> option.
> - Use the same helper function for PV and PVH in order to decide if a
> page should be added to the domain page tables.
> - Use the data inside of the domain struct to detect overlaps with
> emulated MMIO regions.
> ---
> Cc: Andrew Cooper <andrew.cooper3@citrix.com>
> Cc: George Dunlap <George.Dunlap@eu.citrix.com>
> Cc: Ian Jackson <ian.jackson@eu.citrix.com>
> Cc: Jan Beulich <jbeulich@suse.com>
> Cc: Julien Grall <julien.grall@arm.com>
> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> Cc: Stefano Stabellini <sstabellini@kernel.org>
> Cc: Tim Deegan <tim@xen.org>
> Cc: Wei Liu <wei.liu2@citrix.com>
> Cc: Paul Durrant <paul.durrant@citrix.com>
> Cc: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
> Cc: Brian Woods <brian.woods@amd.com>
> Cc: Kevin Tian <kevin.tian@intel.com>
> ---
> docs/misc/xen-command-line.markdown | 9 ++++
> xen/arch/x86/hvm/io.c | 5 ++
> xen/drivers/passthrough/amd/pci_amd_iommu.c | 3 ++
> xen/drivers/passthrough/arm/smmu.c | 4 ++
> xen/drivers/passthrough/iommu.c | 5 +-
> xen/drivers/passthrough/vtd/iommu.c | 3 ++
> xen/drivers/passthrough/x86/iommu.c | 52 ++++++++++++++++++---
> xen/include/asm-x86/hvm/io.h | 3 ++
> xen/include/xen/iommu.h | 2 +-
> 9 files changed, 78 insertions(+), 8 deletions(-)
>
> diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-
> command-line.markdown
> index 98f0f3b68b..1ffd586224 100644
> --- a/docs/misc/xen-command-line.markdown
> +++ b/docs/misc/xen-command-line.markdown
> @@ -704,6 +704,15 @@ This list of booleans controls the iommu usage by
> Dom0:
> option is only applicable to a PV Dom0 and is enabled by default on Intel
> hardware.
>
> +* `map-reserved`: sets up DMA remapping for all the reserved regions in
> the
> + memory map for Dom0. Use this to work around firmware issues providing
> + incorrect RMRR/IVMD entries. Rather than only mapping RAM pages for
> IOMMU
> + accesses for Dom0, all memory regions marked as reserved in the memory
> map
> + that don't overlap with any MMIO region from emulated devices will be
> + identity mapped. This option maps a subset of the memory that would be
> + mapped when using the `map-inclusive` option. This option is available to
> all
> + Dom0 modes and is enabled by default on Intel hardware.
> +
> ### dom0\_ioports\_disable (x86)
> > `= List of <hex>-<hex>`
>
> diff --git a/xen/arch/x86/hvm/io.c b/xen/arch/x86/hvm/io.c
> index 47d6c850ca..a5b0a23f06 100644
> --- a/xen/arch/x86/hvm/io.c
> +++ b/xen/arch/x86/hvm/io.c
> @@ -404,6 +404,11 @@ static const struct hvm_mmcfg
> *vpci_mmcfg_find(const struct domain *d,
> return NULL;
> }
>
> +bool vpci_is_mmcfg_address(const struct domain *d, paddr_t addr)
> +{
> + return vpci_mmcfg_find(d, addr);
> +}
> +
> static unsigned int vpci_mmcfg_decode_addr(const struct hvm_mmcfg
> *mmcfg,
> paddr_t addr, pci_sbdf_t *sbdf)
> {
> diff --git a/xen/drivers/passthrough/amd/pci_amd_iommu.c
> b/xen/drivers/passthrough/amd/pci_amd_iommu.c
> index 073d18bd10..330f9ce386 100644
> --- a/xen/drivers/passthrough/amd/pci_amd_iommu.c
> +++ b/xen/drivers/passthrough/amd/pci_amd_iommu.c
> @@ -256,6 +256,9 @@ static void __hwdom_init
> amd_iommu_hwdom_init(struct domain *d)
> /* Inclusive IOMMU mappings are disabled by default on AMD hardware.
> */
> if ( iommu_hwdom_inclusive == -1 )
> iommu_hwdom_inclusive = 0;
> + /* Reserved IOMMU mappings are disabled by default on AMD
> hardware. */
> + if ( iommu_hwdom_reserved == -1 )
> + iommu_hwdom_reserved = 0;
>
> if ( allocate_domain_resources(dom_iommu(d)) )
> BUG();
> diff --git a/xen/drivers/passthrough/arm/smmu.c
> b/xen/drivers/passthrough/arm/smmu.c
> index a5158b0bdf..43ece42a50 100644
> --- a/xen/drivers/passthrough/arm/smmu.c
> +++ b/xen/drivers/passthrough/arm/smmu.c
> @@ -2732,6 +2732,10 @@ static void __hwdom_init
> arm_smmu_iommu_hwdom_init(struct domain *d)
> printk(XENLOG_WARNING
> "map-inclusive dom0-iommu option is not supported on
> ARM\n");
> iommu_hwdom_inclusive = 0;
> + if ( iommu_hwdom_reserved == 1 )
> + printk(XENLOG_WARNING
> + "map-reserved dom0-iommu option is not supported on
> ARM\n");
> + iommu_hwdom_reserved = 0;
> }
>
> static void arm_smmu_iommu_domain_teardown(struct domain *d)
> diff --git a/xen/drivers/passthrough/iommu.c
> b/xen/drivers/passthrough/iommu.c
> index 9552464bdc..a29bc13f8a 100644
> --- a/xen/drivers/passthrough/iommu.c
> +++ b/xen/drivers/passthrough/iommu.c
> @@ -62,6 +62,7 @@ bool_t __read_mostly iommu_intremap = 1;
> bool __hwdom_initdata iommu_hwdom_strict;
> bool __read_mostly iommu_hwdom_passthrough;
> int8_t __hwdom_initdata iommu_hwdom_inclusive = -1;
> +int8_t __hwdom_initdata iommu_hwdom_reserved = -1;
>
> /*
> * In the current implementation of VT-d posted interrupts, in some
> extreme
> @@ -155,6 +156,8 @@ static int __init parse_dom0_iommu_param(const
> char *s)
> iommu_hwdom_strict = val;
> else if ( (val = parse_boolean("map-inclusive", s, ss)) >= 0 )
> iommu_hwdom_inclusive = val;
> + else if ( (val = parse_boolean("map-reserved", s, ss)) >= 0 )
> + iommu_hwdom_inclusive = val;
> else
> rc = -EINVAL;
>
> @@ -236,7 +239,7 @@ void __hwdom_init iommu_hwdom_init(struct
> domain *d)
>
> hd->platform_ops->hwdom_init(d);
>
> - ASSERT(iommu_hwdom_inclusive != -1);
> + ASSERT(iommu_hwdom_inclusive != -1 && iommu_hwdom_inclusive != -
> 1);
> if ( iommu_hwdom_inclusive && !is_pv_domain(d) )
> {
> printk(XENLOG_WARNING
> diff --git a/xen/drivers/passthrough/vtd/iommu.c
> b/xen/drivers/passthrough/vtd/iommu.c
> index a09e02c8db..1121f5ff5b 100644
> --- a/xen/drivers/passthrough/vtd/iommu.c
> +++ b/xen/drivers/passthrough/vtd/iommu.c
> @@ -1307,6 +1307,9 @@ static void __hwdom_init
> intel_iommu_hwdom_init(struct domain *d)
> /* Inclusive mappings are enabled by default on Intel hardware for PV. */
> if ( iommu_hwdom_inclusive == -1 )
> iommu_hwdom_inclusive = is_pv_domain(d);
> + /* Reserved IOMMU mappings are enabled by default on Intel hardware.
> */
> + if ( iommu_hwdom_reserved == -1 )
> + iommu_hwdom_reserved = 1;
>
> setup_hwdom_pci_devices(d, setup_hwdom_device);
> setup_hwdom_rmrr(d);
> diff --git a/xen/drivers/passthrough/x86/iommu.c
> b/xen/drivers/passthrough/x86/iommu.c
> index 5809027573..47a078272a 100644
> --- a/xen/drivers/passthrough/x86/iommu.c
> +++ b/xen/drivers/passthrough/x86/iommu.c
> @@ -20,6 +20,7 @@
> #include <xen/softirq.h>
> #include <xsm/xsm.h>
>
> +#include <asm/hvm/io.h>
> #include <asm/setup.h>
>
> void iommu_update_ire_from_apic(
> @@ -139,17 +140,23 @@ static bool __hwdom_init
> hwdom_iommu_map(const struct domain *d,
> unsigned long max_pfn)
> {
> mfn_t mfn = _mfn(pfn);
> + unsigned int i, type;
>
> /*
> * Set up 1:1 mapping for dom0. Default to include only conventional RAM
> * areas and let RMRRs include needed reserved regions. When set, the
> * inclusive mapping additionally maps in every pfn up to 4GB except those
> - * that fall in unusable ranges.
> + * that fall in unusable ranges for PV Dom0.
> */
> - if ( (pfn > max_pfn && !mfn_valid(mfn)) || xen_in_range(pfn) )
> + if ( (pfn > max_pfn && !mfn_valid(mfn)) || xen_in_range(pfn) ||
> + /*
> + * Ignore any address below 1MB, that's already identity mapped by
> the
> + * Dom0 builder for HVM.
> + */
> + (!d->domain_id && is_hvm_domain(d) && pfn < PFN_DOWN(MB(1))) )
> return false;
>
> - switch ( page_get_ram_type(mfn) )
> + switch ( type = page_get_ram_type(mfn) )
> {
> case RAM_TYPE_UNUSABLE:
> return false;
> @@ -160,10 +167,40 @@ static bool __hwdom_init
> hwdom_iommu_map(const struct domain *d,
> break;
>
> default:
> - if ( !iommu_hwdom_inclusive || pfn > max_pfn )
> + if ( type & RAM_TYPE_RESERVED )
> + {
> + if ( !iommu_hwdom_inclusive && !iommu_hwdom_reserved )
> + return false;
> + }
> + else if ( is_hvm_domain(d) || !iommu_hwdom_inclusive || pfn >
> max_pfn )
> return false;
> }
>
> + /*
> + * Check that it doesn't overlap with the LAPIC
> + * TODO: if the guest relocates the MMIO area of the LAPIC Xen should
> make
> + * sure there's nothing in the new address that would prevent trapping.
> + */
> + if ( has_vlapic(d) )
> + {
> + const struct vcpu *v;
> +
> + for_each_vcpu(d, v)
> + if ( pfn == PFN_DOWN(vlapic_base_address(vcpu_vlapic(v))) )
> + return false;
> + }
> + /* ... or the IO-APIC */
> + for ( i = 0; has_vioapic(d) && i < d->arch.hvm.nr_vioapics; i++ )
> + if ( pfn == PFN_DOWN(domain_vioapic(d, i)->base_address) )
> + return false;
> + /*
> + * ... or the PCIe MCFG regions.
> + * TODO: runtime added MMCFG regions are not checked to make sure
> they
> + * don't overlap with already mapped regions, thus preventing trapping.
> + */
> + if ( has_vpci(d) && vpci_is_mmcfg_address(d, pfn_to_paddr(pfn)) )
> + return false;
> +
> return true;
> }
>
> @@ -173,7 +210,7 @@ void __hwdom_init arch_iommu_hwdom_init(struct
> domain *d)
>
> BUG_ON(!is_hardware_domain(d));
>
> - if ( iommu_hwdom_passthrough || !is_pv_domain(d) )
> + if ( iommu_hwdom_passthrough )
> return;
>
> max_pfn = (GB(4) >> PAGE_SHIFT) - 1;
> @@ -187,7 +224,10 @@ void __hwdom_init arch_iommu_hwdom_init(struct
> domain *d)
> if ( !hwdom_iommu_map(d, pfn, max_pfn) )
> continue;
>
> - rc = iommu_map_page(d, pfn, pfn,
> IOMMUF_readable|IOMMUF_writable);
> + if ( paging_mode_translate(d) )
> + rc = set_identity_p2m_entry(d, pfn, p2m_access_rw, 0);
> + else
> + rc = iommu_map_page(d, pfn, pfn,
> IOMMUF_readable|IOMMUF_writable);
> if ( rc )
> printk(XENLOG_WARNING " d%d: IOMMU mapping failed: %d\n",
> d->domain_id, rc);
> diff --git a/xen/include/asm-x86/hvm/io.h b/xen/include/asm-x86/hvm/io.h
> index 8c83fd0c8b..7ceb119b64 100644
> --- a/xen/include/asm-x86/hvm/io.h
> +++ b/xen/include/asm-x86/hvm/io.h
> @@ -185,6 +185,9 @@ int register_vpci_mmcfg_handler(struct domain *d,
> paddr_t addr,
> /* Destroy tracked MMCFG areas. */
> void destroy_vpci_mmcfg(struct domain *d);
>
> +/* Check if an address is between a MMCFG region for a domain. */
> +bool vpci_is_mmcfg_address(const struct domain *d, paddr_t addr);
> +
> #endif /* __ASM_X86_HVM_IO_H__ */
>
>
> diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
> index 89c6830689..57c4e81ec6 100644
> --- a/xen/include/xen/iommu.h
> +++ b/xen/include/xen/iommu.h
> @@ -37,7 +37,7 @@ extern bool_t iommu_debug;
> extern bool_t amd_iommu_perdev_intremap;
>
> extern bool iommu_hwdom_strict, iommu_hwdom_passthrough;
> -extern int8_t iommu_hwdom_inclusive;
> +extern int8_t iommu_hwdom_inclusive, iommu_hwdom_reserved;
>
> extern unsigned int iommu_dev_iotlb_timeout;
>
> --
> 2.18.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 14+ messages in thread* Re: [PATCH v8 6/6] x86/iommu: add map-reserved dom0-iommu option to map reserved memory ranges
2018-09-07 9:07 ` [PATCH v8 6/6] x86/iommu: add map-reserved dom0-iommu option to map reserved memory ranges Roger Pau Monne
2018-09-10 11:31 ` Julien Grall
2018-09-11 7:50 ` Paul Durrant
@ 2018-09-12 11:59 ` Suravee Suthikulpanit
2 siblings, 0 replies; 14+ messages in thread
From: Suravee Suthikulpanit @ 2018-09-12 11:59 UTC (permalink / raw)
To: Roger Pau Monne, xen-devel
Cc: Kevin Tian, Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk,
George Dunlap, Andrew Cooper, Ian Jackson, Tim Deegan,
Julien Grall, Paul Durrant, Jan Beulich, Brian Woods
On 9/7/18 4:07 PM, Roger Pau Monne wrote:
> Several people have reported hardware issues (malfunctioning USB
> controllers) due to iommu page faults on Intel hardware. Those faults
> are caused by missing RMRR (VTd) entries in the ACPI tables. Those can
> be worked around on VTd hardware by manually adding RMRR entries on
> the command line, this is however limited to Intel hardware and quite
> cumbersome to do.
>
> In order to solve those issues add a new dom0-iommu=map-reserved
> option that identity maps all regions marked as reserved in the memory
> map. Note that regions used by devices emulated by Xen (LAPIC, IO-APIC
> or PCIe MCFG regions) are specifically avoided. Note that this option
> is available to all Dom0 modes (as opposed to the inclusive option
> which only works for PV Dom0).
>
> Signed-off-by: Roger Pau Monné<roger.pau@citrix.com>
> Reviewed-by: Kevin Tian<kevin.tian@intel.com>
> Reviewed-by: Wei Liu<wei.liu2@citrix.com>
> Acked-by: Jan Beulich<jbeulich@suse.com>
> ---
> Changes since v7:
> - Don't use true/false with int8_t.
> - Print a warning message if map-reserved is set on ARM.
>
> Changes since v6:
> - Reword the map-reserved help to make it clear it's available to
> both PV and PVH Dom0.
> - Assign type inside of the switch expression.
> - Remove the comment about IO-APIC MMIO relocation, this is not
> supported ATM.
>
> Changes since v5:
> - Merge with the vpci MMCFG helper patch.
> - Add a TODO item about the issues with relocating the LAPIC or
> IOAPIC MMIO regions.
> - Use the newly introduced page_get_ram_type that returns all the
> types that fall between a page.
> - Use paging_mode_translate instead of iommu_use_hap_pt when deciding
> whether to use set_identity_p2m_entry or iommu_map_page.
>
> Changes since v4:
> - Use pfn_to_paddr.
> - Rebase on top of previous changes.
> - Change the default option setting to use if instead of a ternary
> operator.
> - Rename to map-reserved.
>
> Changes since v3:
> - Add mappings if the iommu page tables are shared.
>
> Changes since v2:
> - Fix comment regarding dom0-strict.
> - Change documentation style of xen command line.
> - Rename iommu_map to hwdom_iommu_map.
> - Move all the checks to hwdom_iommu_map.
>
> Changes since v1:
> - Introduce a new reserved option instead of abusing the inclusive
> option.
> - Use the same helper function for PV and PVH in order to decide if a
> page should be added to the domain page tables.
> - Use the data inside of the domain struct to detect overlaps with
> emulated MMIO regions.
> ---
> Cc: Andrew Cooper<andrew.cooper3@citrix.com>
> Cc: George Dunlap<George.Dunlap@eu.citrix.com>
> Cc: Ian Jackson<ian.jackson@eu.citrix.com>
> Cc: Jan Beulich<jbeulich@suse.com>
> Cc: Julien Grall<julien.grall@arm.com>
> Cc: Konrad Rzeszutek Wilk<konrad.wilk@oracle.com>
> Cc: Stefano Stabellini<sstabellini@kernel.org>
> Cc: Tim Deegan<tim@xen.org>
> Cc: Wei Liu<wei.liu2@citrix.com>
> Cc: Paul Durrant<paul.durrant@citrix.com>
> Cc: Suravee Suthikulpanit<suravee.suthikulpanit@amd.com>
> Cc: Brian Woods<brian.woods@amd.com>
> Cc: Kevin Tian<kevin.tian@intel.com>
For AMD-related changes.
Acked-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Thank you,
Suravee
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 14+ messages in thread